TWI239163B - Method and apparatus to provide data traffic control - Google Patents

Method and apparatus to provide data traffic control Download PDF

Info

Publication number
TWI239163B
TWI239163B TW92116415A TW92116415A TWI239163B TW I239163 B TWI239163 B TW I239163B TW 92116415 A TW92116415 A TW 92116415A TW 92116415 A TW92116415 A TW 92116415A TW I239163 B TWI239163 B TW I239163B
Authority
TW
Taiwan
Prior art keywords
data
size
routing
controller
symbol bucket
Prior art date
Application number
TW92116415A
Other languages
Chinese (zh)
Other versions
TW200408226A (en
Inventor
Puqi Tang
Original Assignee
Intel Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority to US10/173,909 priority Critical patent/US7447155B2/en
Application filed by Intel Corp filed Critical Intel Corp
Publication of TW200408226A publication Critical patent/TW200408226A/en
Application granted granted Critical
Publication of TWI239163B publication Critical patent/TWI239163B/en

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic regulation in packet switching networks
    • H04L47/10Flow control or congestion control
    • H04L47/36Evaluation of the packet size, e.g. maximum transfer unit [MTU]
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic regulation in packet switching networks
    • H04L47/10Flow control or congestion control
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic regulation in packet switching networks
    • H04L47/10Flow control or congestion control
    • H04L47/11Congestion identification
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic regulation in packet switching networks
    • H04L47/10Flow control or congestion control
    • H04L47/22Traffic shaping
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic regulation in packet switching networks
    • H04L47/10Flow control or congestion control
    • H04L47/28Flow control or congestion control using time considerations
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/54Store-and-forward switching systems
    • H04L12/56Packet switching systems
    • H04L12/5601Transfer mode dependent, e.g. ATM
    • H04L2012/5629Admission control
    • H04L2012/5631Resource management and allocation
    • H04L2012/5636Monitoring or policing, e.g. compliance with allocated rate, corrective actions
    • H04L2012/5637Leaky Buckets

Abstract

According to an embodiment of the invention, a data controller comprises a traffic pattern collector to observe a data traffic pattern, the data traffic being comprised of data packets; a traffic service engine to receive data from the traffic controller concerning the data traffic pattern and to determine a data flow specification for the data traffic pattern, the received data including the size and arrival time of each of the data packets; and a quality of service provider to receive the data flow specification. The data flow specification is the minimum data flow specification data flow specification that will allow each of the data packets to be transferred by the traffic controller within a delay upper bound. According to one embodiment, the minimum data flow specification for the data traffic pattern is determined according to an algorithm known as the Any-Delay TB Algorithm.

Description

1239163 发明 Description of the invention: [Technical field to which the invention belongs] A specific embodiment of the present invention relates generally to a data network, and more specifically, to a guarantee service on the data network. [Previous technology] In data networks, "quality of service" (QoS) refers to the services provided to network routing. A special type of service quality is "guaranteed services," in which the 'point-to-endpoint delay of data transmission' It is guaranteed not to exceed a certain delay ceiling or limit. Guaranteed services are particularly important for services that include mission-critical communications, including: Voice over Internet technology (Voice over IP or V0IP), where an Internet connection is used to transmit voice data; and a virtual personal network (VpN), where the Internet or another public communication medium is used for the transmission of personal network data. In order to guarantee the end-to-end delay cap for data routing on the data path, each node along the data path must guarantee a delay cap, and the total delay cap of each node is limited to the end-to-end delay Ceiling. A data routing capability system available at a network node is a symbol bucket. However, in order to use a routing capability system such as a symbol bucket sub-model in the network and ensure compliance with the upper delay limit, the minimum parameters need to be established for the routing capability system. The minimum required parameter that allows the system to stay within the upper delay limit is based on the data routing pattern encountered. In traditional network routing systems, there is no efficient and effective mechanism for determining the minimum parameters required in order to meet the service requirements of a special data routing pattern. [Summary of the Invention] 86196 1239163-a data controller, including:-a routing pattern collector to observe a data routing pattern, the data routing includes a plurality of data packets; a routing service engine to receive from the routing pattern collector Regarding the data of the data routing pattern, and determining the data flow specifications of the data routing pattern, the received data includes the size of each of these data packets, the time of arrival; and the service provider's. Alpha Bay receives the data stream specification, and the f stream specification represents the smallest data stream specification that will allow each data packet to be transferred by the data controller in the middle of the delay. [Embodiment] The described method and device are guarantee services for data networks. In the following description, 'for the sake of illustration, many specific details are described. However, it will be understood that specific embodiments of the invention may be practiced without these specific details. In other examples, well-known circuits, structures, technologies, and devices are not shown in detail. Specific embodiments of the present invention include various processes and will be described below. These processes can be performed through hardware components, or they can be implemented in machine-executable instructions' and can be used to cause general-purpose or special-purpose processors, or logic circuits programmed using instructions to perform the processes. Alternatively, processing can be performed through a combination of hardware and software. A single definition of the exemplary environment of the embodiment: Before describing the various implementations of the invention, some of the terms used in this patent will be 86196 1239163. As used herein, "quality of service," or "QOS" means The quality of service provided to the network data routing. As used herein, "guaranteed service" means the quality of service that guarantees that the end-to-end delay of the data stream does not exceed the upper limit. According to a specific embodiment of the present invention, a data routing pattern is transmitted over a network, and the network routing includes a data packet. According to a specific embodiment of the present invention, the network includes a routing control system to control data routing flow. According to a specific embodiment of the present invention, the network is a symbol bucket sub-controller model used in the routing control system. According to a specific embodiment of the present invention, an upper limit indicates the delay of data routing, and using information about the routing pattern, the parameters of the routing control system are determined such that no data packet delay will exceed the upper limit. In a particular embodiment, the determined parameter is the size of the symbol bucket. According to a specific embodiment of the present invention, the determined parameter is the smallest parameter to ensure that the operation conforms to the upper delay limit. In the specific embodiment of the present invention, a routing pattern collector collects the original routing graph t from a network data stream and passes the related routing patterns to a measurement-based routing specification (TS) engine. According to specific examples, the engine converts the original routing pattern data into stream specifications and provides the specifications to the qgs service provider. Stream specifications ^ system specifications. In the specific embodiment of the route control basic principle of Du Qinzhu, the processing of the routing pattern is performed in the real-time I-rate network. The use of data routing controls for real-time processing is more important for maintaining the efficiency of the processing algorithm while maintaining the 'manipulation'. In the specific embodiment of the present invention, a symbol bucket sub-controller is used for 86196 1239163 by & symbol bucket sub-data controllers used in routing generators, switches, routers, and other network devices to allow data packets. Limited delay. According to a specific embodiment, the delayed data packet is temporarily stored in a queue related to the control of the symbol bucket. For a specific route and a specified upper delay limit, the establishment of symbol bucket sub-parameters can ensure that no data packet delay will exceed the upper limit. In particular, the size parameter of a symbol bucket can be determined to be the minimum size, and it is guaranteed that the upper back delay limit is not reached. Figure 1 depicts a symbol bucket model used in connection with a specific embodiment of the present invention. In this example, a transmitting device 105 sends data 2 to a receiving device 115 over a communication path 110. The transmitting device 105 and the receiving device 115 may be any devices or systems of the Hiroshi, Kushiro, including any network server, switch, client system, or other devices or systems. Data is transmitted as data packets, which can be resized and arrive at various times. What is the size of the data packet shown in Figure i? The first data packet 120 of 1 arrives at time t1; the second data packet 125 of size " arrives at time t2; the third data packet 13 of size p3 arrives at time t3 and size p4 The fourth data packet 13 5 arrived at time t4. As shown in Figure 1, changes in the size of the data packet and the arrival time will cause a certain time period with the least action and a certain time period with the data, burst, and. The data packet can be processed by a flow controller using a schedule counter, which can be described as a symbolic logic of a bluff bucket. In this example, the symbol bucket ^ 0 receives symbols from a symbol generator 145 periodically. The symbol bucket control &# 1 can complete the data stream. The symbol bucket controller allows certain data to be dropped, 86196 1239163, such as the representation of the second data packet 125, the third data packet 130, and the fourth data packet 135 that arrive in sequence in FIG. 1, but the system will limit the possible cars. Big shell material is bursting. The level of the data stream can be adjusted through symbols. For the number of special bytes of recovery ... net, one symbol can be used, and the bucket 140 is removed. In a particular embodiment, a symbol is needed for each data byte recovered. A symbol generation rate ^ indicates the number of pay numbers generated by each temple gate unit. Symbol bucket 1 can hold a certain maximum number of symbols b (that is, the capacity of the symbol bucket). According to the example shown in Figure 1, when there are sufficient symbols in the symbol bucket of the number of bytes contained in the data packet, the arriving data packet can be recovered. If there are not enough symbols available at any time to recover the data packet, the data packet will be maintained or stored in a row, 5 until the symbol generator 1 4 5 generates enough symbols in the bucket 14 0 to allow transmission. . In a particular embodiment, the symbol bucket 14o includes a parameter (r, b), where r is the symbol bucket rate and b is the symbol bucket size. In the specific embodiment of the present invention, the queue 150 for a symbol bucket is large enough to hold any reserved data packets. The observed routing pattern will have some of the largest data packet size in ❿. In a specific embodiment of the present invention, the symbol generator 145 and the symbol bucket 1 40 include a counter, which can be incremented at a fixed rate Γ of the maximum count of b. The counter can be decremented for each data packet recovered, for example, decremented by 1 for each byte recovered. If the counter does not recover enough counts from the data packet, the data packet will remain in queue 1 50 until the counter reaches a sufficient count. However, keeping data packets in queue for 150 will cause data delays. If 86196 1239163 stipulates an upper limit for the data delay, there will be a question about the minimum size required for the symbol bucket. In order to determine that the upper limit of the delay will not exceed any guaranteed service for data packets. FIG. 2 is a block diagram of the measurement-based routing specification system 2000 operation in a specific embodiment of the present invention. System 200 can exist at any observation point on the network. In this example, the data in the form of a data packet is transmitted as shown in point A 2005 from the network to the next point indicated by point B 2 0. The data route is passed to the second point 21 through the route pattern collector 215 and the QoS provider 220. The routing pattern collector 215 collects information about routing patterns and provides the information to a measurement-based routing specification (MBTS) engine 225. The information includes the number of data packets received, the size of each data packet, and the time it takes for each data packet to reach the routing pattern collector 2 丨 5. The MBTS engine 225 疋 converts raw information about data patterns into data stream specifications. In the specific embodiment of the present invention, the cargo flow specification determined by the MBTS engine 225 is the optimal symbol bucket parameter form of the data routing pattern. The results determined by the MBTS engine 225 are then available to the QoS service provider 220 via a reporting authority 23. Note that in this description, to help explain, the routing pattern collector 215, the QoS service provider 220, the MBTS engine 225, and the reporting organization 230 are generally discussed with each being a single functional unit. However, the functions performed by these various elements are different from those previously described which can be combined or disperse. For example, any function may be implemented on any number of logical or physical devices, or a single logical or physical device. FIG. 3 is a block diagram of a network structure including a specific embodiment of the present invention. Figure 3 is a simplified example 'but specific embodiments of the present invention can be implemented in many different environments. FIG. 3 depicts a network 300 including one or more servers. In this example, the network 300 shown includes a first server 305, a second server 310, and a third server 315. The network includes one or more clients, such as a first client 320, a second client 325, and a third client 33, as shown in FIG. In this example, the network devices are connected by switches 335 and 340 and by routers 345, and 355. In an exemplary aspect, the first client 32 may request certain information. In this example, the requested data may be supplied from multiple sources, including a first server 305 and a second server 310. With the data routing control in the specific embodiment of the present invention, the data routing of the network can be measured at any point on the network. According to a specific embodiment of the present invention, the switch 335 can sense data routes related to the first server and the second server 310. In particular, the number of routes can be determined at any time, including whether there is a high level of routing. By using the routing data information, the data load on the first server 305 and the second server 31 can be adjusted or balanced, as needed, to ensure that the data routing does not exceed the upper limit of the data delay. According to a rich embodiment of the present invention, # when the data is supplied to the network, the third feeder 315 will be subject to the contour, which includes restrictions on the data transmission rate, and data routing from the server. Send ". A viewing point can be applied at switch 340 to determine the characteristics of the routing pattern. Li Taishuang ^, Mi , f 太 In the specific embodiment of the present invention,

A data controller can control the routing, so that you A can maintain the required wheel corridor when Cui Bao guarantees that the service is provided so that the data delay will exceed a certain limit. In the specific embodiment of the present invention, one set of two buckets can be used in one data controller for the routing flow of data packets. The bucket has at least the data that is equal to the average data routing flow. rate. The route > b is composed of n data packet groups 86196 -11-1239163. Each packet in the routing stream has a special size and arrives at a special time. To determine the macro μ &, the size of the bucket can ensure that any packet delay in the route does not exceed the specified upper limit, and some calculations can be performed from the following: Each packet is already executed. In the specific embodiment of the present invention, the calculation can be performed as the data packet is observed. The result of this calculation is that the symbol buckets, large J > 胄 纟 small parameters are the minimum symbol bucket size, and JL meets the delay upper limit requirement. In a specific embodiment of the present invention, the symbol bucket size parameter of a specific delay upper limit is calculated according to an algorithm represented by “any delay, delay, delay, delay, delay, delay, delay, delay, delay, delay, delay, delay, delay, delay, or delay.” One character rides the name ^ _ 卞 Tiger bucket. In the specific embodiment of the present invention, the size parameter of the pay bucket can be determined according to the following formula: symbol bucket rate = r ', where the data rate is at least equal to the data stream Average data rate> D = Maximum delay b, d, and m integer variables, where: b = Significant position of the bucket size. Mean value m = middle m becomes—the maximum packet size of a particular routing pattern. Data routing packets are possible. The data described as: (A ,,), (P2, t2), ..., (pn, tn) which represents a data stream with n data packets, where the data packet is expected to have a size of one byte, and is Arrived at time ^. By using this term, the relationship between the symbol bucket rate and the average data rate can be expressed by the following formula: 86196 -12-1239163 r > Σ > ΐ, in the specific embodiment of the present invention, the data packet is composed of data packets. A special

而言 In terms of routing patterns, the size of a symbol bucket can be determined by the following virtual code: b = d = prr · D

For k =: 2 to nd = maX [d + Pk-r · "Eight 丨", Pk, Pk_r · (tk + D, i), r · D] b: =: max (b5 d) m = max ( pk, m)} b = max (b, m) FIG. 4 is a parameter selection of a symbol bucket described in the specific embodiment of the present invention. According to the specific embodiment of the present invention, a routing pattern including a data packet is included. It is observed in processing block 405. The first data packet is evaluated in processing block 410. In processing block 415, the first variable b and the second variable d are initially the first data packet minus the symbol bucket rate multiplied by the upper delay limit. d is set. At processing block 420, the third variable m, which is finally equal to the maximum packet size of the routing flow, is initially set by the size of the first data packet. According to a specific embodiment of the present invention, a series of calculations (or loops) is Executed in data packets 2 to n. In processing block 425 starting from the second data packet, each of this data packet is evaluated in the processing block. For each of this data packet, the 'variable d' is set in processing block 435 Into a maximum of three numbers. 86196 -13- 1239163 The number is equal to the variable ㈣ previous value plus the current The size of the data packet minus the bucket rate multiplied by s between the current data packet time and the previous data packet time. The second number is equal to the size of the previous data packet, plus the size of the data packet, minus the sign The bucket rate is multiplied by a number, where the number of ^ is equal to the current data packet time plus the maximum delay of the packet, and the last and last packet times are eliminated. The third number is equal to the size of the current packet minus the symbol bucket rate multiplied by the maximum delay D In processing block 440, the variable b is set to the previous maximum value of the variable b ... or = the current maximum value of the number d. In processing block 445, the variable is the maximum value set to the current data packet or the maximum previous value of the variable Value. When the claw is set to the maximum value of the current data packet size, or the previous maximum size, after all data packet evaluations, it will not be equal to the maximum data packet size. There is additional data in processing box 4 50 The packet is to be evaluated and the next data packet is selected in processing block 455. After a series of calculations are performed for each data packet in processing block 45, the symbol bucket is large The small parameter b in the processing block 460 will be the maximum previous value of the variable b, or the current maximum value of the variable ^^. In the specific embodiment of the present invention, the determined value of the variable 13 may represent the minimum symbol bucket size 'and may satisfy The upper limit of the delay. In the specific embodiment of the present invention, the loop of the algorithm for calculating the size parameter of the symbol bucket will only calculate n- 丨 times. For this reason, in terms of time, the algorithm complexity is 0 (n ), Which indicates that the computational complexity linearity is related to the number of data packets in the routing pattern. In the specific embodiment of the present invention, the space required for the calculation of the symbol bucket size parameter includes only three integer variables d, b, and m . Therefore, in terms of space, the complexity of the algorithm is 0 (1), which means that the memory required for the calculation of 86196 -14-1239163 is constant. The linear complexity of the calculation and the fixed memory requirements indicate that the calculation used to build the size of the symbol bucket is very efficient and lightweight, so it has a small impact on the operation of the system. Appendix Additional details on any of the above delayed TB algorithms are provided in Appendix A. The invention is described in terms of several specific embodiments. However, those skilled in the art can understand that the present invention is not limited to the specific embodiments described, but that modifications and changes can be achieved without departing from the broad spirit and scope of the present invention. Specifications and drawings are illustrative and not restrictive. [Simplified description of the drawings] The present invention can be better understood through the following descriptions of specific embodiments of the present invention, in which: Tian FIG. 1 说明 operation instructions of the symbol bucket under the specific embodiment of the present invention; FIG. 2 疋The routing specification technology in the specific embodiment of the invention; and FIG. 30 is a flowchart illustrating the optimal symbol bucket size using a network structure example of the specific embodiment of the invention to illustrate FIG. 4. [Illustration of Symbols in the Schematic Diagram] 105 115 145 140 135 '130, 125, 150 345, 320, communication path

Measurement-based routing specification system Point A

Measurement-oriented routing specification engine Routing pattern collector Reporting organization QoS provider Point B 3 1 0, 3 1 5 Server 340 Switch 350, 355 Router 325, 330 Client 86196 16

Claims (1)

  1. In the J239J ^ 2l64l5 patent application, k: Replacement of the patent application scope (October 1993) Pick up and apply for a patent garden: 1. A data controller, which includes: a routing pattern collector to observe a data routing pattern , The data routing includes a plurality of data packets;-a routing service engine to receive data about the data routing pattern from the routing pattern collector, and determine the data flow specifications of the data routing pattern, the received data includes the data The size and arrival time of each of the packets; and ^ the quality of the service provider receives the data stream specifications. The minimum data stream performance of the data stream specifications will allow each data packet to be transferred by the data controller in the middle of the maximum delay. specification. 2. The data controller according to item 1 of the scope of patent application, further comprising a reporting mechanism 'to report the data stream specification to the service quality provider. 3. If the data controller in the scope of the patent application, the data controller includes a symbol bucket, and the data stream specification includes a minimum symbol bucket size that meets the upper delay limit. 4. The data controller of item 3 of the patent application, wherein the size of the symbol bucket is based at least in part on the size and arrival time of the data packets. 5 · If the data controller of item 4 of the patent application scope, wherein the data controller only considers each data packet once in determining the size of the symbol bucket. 6 · A method for controlling data routing, including: Observing a data routing pattern, the data routing pattern including a stream of data packets; determining information about the data routing pattern, the information including the size of the data packets These data are sealed 4g. 4t ^ ^ ^ Arrival time of one of the daggers; and according to the value of the data map of the child information, the value of the decision parameter is: 7 to decide-the routing control sends the data routing without any (Forecasting 4 network device transmission limit. The delay of the packet will exceed one delay. For example, if the method in the scope of patent application No. 6 is applied, the packet will be further included: the information related to the network device ^ ^ ^ 1, each of which is a routing control parameter. The parameter value of the decision is sufficient. 8. If the patent application scope of the sixth item is too high, go to 'where the routing control parameter contains the size of a bucket. 9. If the patent application scope is eight items. In the method, when the data packet is observed, the calculations of determining the size of the symbol bucket will be performed. Ίο. For example, the method of item 9 of the patent scope, in which the determination time of the symbol bucket size is complicated. Degree 疋 Q⑻, and where the computational space complexity of determining the size of the symbol bucket is 0 (1). 11. The machine is a master medium 'The machine-readable medium has shell material stored in the representation τ sequence, when When the processor executes the data of the instruction sequence, the processor can cause the processor to perform the following operations, including: viewing a data routing pattern, the data routing pattern including a data packet; determining information about the data routing pattern, the data Including the size of each of the data packets, and the arrival time of each of the data packets; and determining a routing control parameter value based on the information about the routing pattern of the data, the parameter value determined by far is the smallest parameter value In order to enable a network device 86196-931029.doc 1239163 to transmit data routing without any data packet delay exceeding a delay limit. I2. If the media of item η of the scope of patent application, it further includes: will ... The routing control parameter of a data routing controller related to the road device is set to the determined parameter value. 13. As in the media of the patent application, the routing control parameter includes a symbol bucket size. H. If applied The media in item 13 of the patent fan garden, in which the calculation of the size of the barrel of the shirt symbol is performed in real time. 15. · The media of item 14 in the scope of the patent application 'where the complexity of the calculation of the size of the barrel of the symbol is Time is linear and fixed space. 16 · —A method for controlling data routing, which includes ... Observe a routing pattern containing n data packets The size and arrival time of this data packet are (Pl, tl), (P2, t2), ..., (Pn, tU depends on the size of the symbol bucket used in the data routing controller. The size of this decision is the smallest Size, so that the data routing controller transmits each data packet in the delay upper limit. 17. The method of item 6 of the patent scope, such as the symbol bucket rate is ", and the child delay upper limit is D, And the determination of the size of the bucket of the symbol includes: For the first data packet, where 1 ·· sets the value of the variable d and the variable b according to the following formula: b = d = pj.r D, and the following formula Set the value of variable m:; A 86196-931029.doc 1239163 For each of the second to eleventh data packets, where k = 2 to η, to perform the following calculations: d maX [d + Pk_r ( tk-tk-i), pk-i + Pk-r (tk + D-tu), pk-r D], b = max (b, d), and m = max (pk, m). 18. The method of claim 17 in the scope of patent application, wherein the size of the symbol bucket is a variable b calculated according to the following formula: b = max (b, m) 〇19_ A machine-readable medium, the machine-readable medium stores a representation For the sequence data, when the processor executes the data of the instruction sequence, the processor can cause the processor to perform the following operations, including: Observe a routing pattern containing n data packets. The size and arrival time of this data packet are (Pl , Tl), (p2, t2), ..., (pn, tn); and the size of the symbol bucket used in a data routing controller, the determined size is the smallest size to allow the data routing The controller transmits each data packet in the delay cap. 20. The media according to item 19 of the patent application scope, wherein the symbol bucket rate is ", and the delay upper limit is D, and wherein the size of the symbol bucket is included. For the first data packet, where k = 1: Q. Set the value of variable d and variable b according to the following formula: b = d = pj-r D, and set the value of variable m according to the following formula: For each of the second to ^ data packets In terms of which 2 to 86196-931029.doc 1239163 n, to perform the following calculations: d—maX [d + Pk-r ⑴ 七]), Pk] + pk-r (tk + D-tw), pk- r D], b = max (b, d), and m = max (pk, m). 21 · As for the media in the scope of patent application No. 20, wherein the size of the symbol bucket is a variable b calculated according to the following formula: b = max (b, m) 〇22 · —a computer network, including: Multiple servers; a plurality of network devices, including a first network device; and a symbol bucket data routing controller for sensing data routes related to the first network device, the routing controller includes · A routing pattern collector to observe the data pattern related to the first network device, the data contains a plurality of data packets, and a routing service engine to receive information from the routing pattern collector regarding the data routing, and determine the The size of the symbol bucket, a quality service provider to receive the determined symbol bucket size, the symbol bucket size represents the minimum symbol bucket size to allow each of these data packets to be included in the delay cap Transmitted through the routing controller; and a reporting mechanism to report the symbol bucket size to the quality of service provider. 23. If the computer network of item 22 of the patent application scope, the size of the symbol bucket is at least the size and arrival time of the packet according to the data. 86196-931029.doc 1239163 ya ο .. 29 24. If the computer network of the 23rd scope of the application for a patent, the data routing controller only considers each data packet once when determining the size of the symbol bucket. 25. A data routing controller, comprising: an observation device for observing the flow of data packets on the network; a decision device for determining information related to the data packets, the information including each data The size and arrival time of the packet; and a determining device for determining the data stream specification, which is the minimum specification to allow each data packet to be transmitted within the delay limit. 26. The data routing controller according to item 25 of the patent application scope, wherein the determined data mud specifications include a symbol bucket size. 27. The data routing controller of item 26 of the patent application, wherein the symbol bucket size is based at least in part on the size and arrival time of the data packet. 28. For example, the data routing controller in the scope of patent application No. 27, wherein the decision device for determining the routing control specification includes a consideration device. When using M to determine, each data packet is considered only once. Luo ’, where the data stream is 29. • If the data routing control item No. 28 of the patent application scope is determined, the decision is made in real time. 86196-931029.doc -6-
TW92116415A 2002-06-17 2003-06-17 Method and apparatus to provide data traffic control TWI239163B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US10/173,909 US7447155B2 (en) 2002-06-17 2002-06-17 Guaranteed service in a data network

Publications (2)

Publication Number Publication Date
TW200408226A TW200408226A (en) 2004-05-16
TWI239163B true TWI239163B (en) 2005-09-01

Family

ID=29733451

Family Applications (1)

Application Number Title Priority Date Filing Date
TW92116415A TWI239163B (en) 2002-06-17 2003-06-17 Method and apparatus to provide data traffic control

Country Status (6)

Country Link
US (1) US7447155B2 (en)
EP (1) EP1514389A1 (en)
CN (1) CN100592707C (en)
AU (1) AU2003243483A1 (en)
TW (1) TWI239163B (en)
WO (1) WO2003107607A1 (en)

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7447155B2 (en) 2002-06-17 2008-11-04 Intel Corporation Guaranteed service in a data network
US7289447B2 (en) * 2003-10-21 2007-10-30 Comcast Cable Holdings, Llc Method and packet-level device for traffic regulation in a data network
US20050174944A1 (en) * 2004-02-10 2005-08-11 Adc Broadband Access Systems, Inc. Bandwidth regulation
GB2411492B (en) * 2004-02-25 2006-06-07 Patsystems Electronic trading system
US20070097864A1 (en) * 2005-11-01 2007-05-03 Cisco Technology, Inc. Data communication flow control
US8171478B2 (en) 2006-06-22 2012-05-01 Marvell International Ltd. Method for packet flow control using credit parameters with a plurality of limits
CN100450102C (en) * 2006-10-09 2009-01-07 华为数字技术有限公司 Method and apparatus for multiuser QOS dispatching
US8843592B2 (en) 2006-12-20 2014-09-23 Omx Technology Ab System and method for adaptive information dissemination
US20080155015A1 (en) 2006-12-20 2008-06-26 Omx Technology Ab Intelligent information dissemination
US7894436B1 (en) * 2007-09-07 2011-02-22 Meru Networks Flow inspection
US8837285B2 (en) * 2008-02-01 2014-09-16 Interdigital Patent Holdings, Inc. Method and apparatus for initializing, preserving, and reconfiguring token buckets
US8462674B2 (en) * 2009-06-04 2013-06-11 Broadcom Corporation Method and system for symmetric transmit and receive latencies in an energy efficient PHY
US8477610B2 (en) 2010-05-31 2013-07-02 Microsoft Corporation Applying policies to schedule network bandwidth among virtual machines
US20120127864A1 (en) * 2010-11-22 2012-05-24 Avaya Inc. Performing policing operations in packet time
CN102420773A (en) * 2012-01-05 2012-04-18 北京网御星云信息技术有限公司 Token-bucket-algorithm-based data transmission method and traffic control device
US9203711B2 (en) * 2013-09-24 2015-12-01 International Business Machines Corporation Port mirroring for sampling measurement of network flows
CN107465629A (en) * 2016-06-06 2017-12-12 中兴通讯股份有限公司 Method for limiting speed and device

Family Cites Families (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5289462A (en) * 1992-08-19 1994-02-22 International Business Machines Corp. Traffic management in packet communications networks
US5408465A (en) * 1993-06-21 1995-04-18 Hewlett-Packard Company Flexible scheme for admission control of multimedia streams on integrated networks
US5831971A (en) * 1996-08-22 1998-11-03 Lucent Technologies, Inc. Method for leaky bucket traffic shaping using fair queueing collision arbitration
US6147970A (en) * 1997-09-30 2000-11-14 Gte Internetworking Incorporated Quality of service management for aggregated flows in a network system
US6112241A (en) * 1997-10-21 2000-08-29 International Business Machines Corporation Integrated network interconnecting device and probe
US6690647B1 (en) * 1998-01-30 2004-02-10 Intel Corporation Method and apparatus for characterizing network traffic
US6643260B1 (en) * 1998-12-18 2003-11-04 Cisco Technology, Inc. Method and apparatus for implementing a quality of service policy in a data communications network
US6449255B1 (en) * 1999-04-26 2002-09-10 Cisco Technology, Inc. Method and apparatus for managing packets using a real-time feedback signal
US6771646B1 (en) * 1999-06-30 2004-08-03 Hi/Fn, Inc. Associative cache structure for lookups and updates of flow records in a network monitor
JP2001230810A (en) * 2000-02-16 2001-08-24 Fujitsu Ltd Packet flow controller and its method
US6868062B1 (en) * 2000-03-28 2005-03-15 Intel Corporation Managing data traffic on multiple ports
US6904014B1 (en) * 2000-04-27 2005-06-07 Cisco Technology, Inc. Method and apparatus for performing high-speed traffic shaping
US6826150B1 (en) * 2000-04-30 2004-11-30 Dipankar Bhattacharya Distriburted QoS policing system and method
US7002918B1 (en) * 2000-05-22 2006-02-21 Northrop Grumman Corporation Method and apparatus for real time scheduling in a satellite communications network
US6958977B1 (en) * 2000-06-06 2005-10-25 Viola Networks Ltd Network packet tracking
EP1187399B1 (en) * 2000-09-11 2008-12-10 Lucent Technologies Inc. Method and a device for controlling source specific data flow
US6973622B1 (en) * 2000-09-25 2005-12-06 Wireless Valley Communications, Inc. System and method for design, tracking, measurement, prediction and optimization of data communication networks
US6904020B1 (en) * 2000-11-01 2005-06-07 Agilent Technologies, Inc. System and method for monitoring communication networks using data stream characterization
JP4403348B2 (en) * 2000-12-14 2010-01-27 ソニー株式会社 Communication apparatus and communication method
US6373824B1 (en) * 2000-12-29 2002-04-16 Intel Corporation Network traffic specification
US6925055B1 (en) * 2001-03-05 2005-08-02 Advanced Micro Devices, Inc. Systems and methods for traffic shaping
US6901050B1 (en) * 2001-03-05 2005-05-31 Advanced Micro Devices, Inc. Systems and methods for flow-based traffic shaping
US7447155B2 (en) 2002-06-17 2008-11-04 Intel Corporation Guaranteed service in a data network
US7130917B2 (en) * 2002-09-26 2006-10-31 Cisco Technology, Inc. Quality of service in a gateway

Also Published As

Publication number Publication date
US7447155B2 (en) 2008-11-04
CN1663195A (en) 2005-08-31
EP1514389A1 (en) 2005-03-16
TW200408226A (en) 2004-05-16
WO2003107607A1 (en) 2003-12-24
AU2003243483A1 (en) 2003-12-31
US20030231648A1 (en) 2003-12-18
CN100592707C (en) 2010-02-24

Similar Documents

Publication Publication Date Title
Qiu et al. EABS: An event-aware backpressure scheduling scheme for emergency Internet of Things
KR102104047B1 (en) Congestion control in packet data networking
CN106165354B (en) Network path selection using bandwidth prediction
Noormohammadpour et al. Datacenter traffic control: Understanding techniques and tradeoffs
Prabhavat et al. On load distribution over multipath networks
Brun et al. Big data for autonomic intercontinental overlays
Awduche et al. Overview and principles of Internet traffic engineering
Cao et al. Assembling TCP/IP packets in optical burst switched networks
Bonomi et al. The rate-based flow control framework for the available bit rate ATM service
Roberts Internet traffic, QoS, and pricing
EP1646192B1 (en) Packet switch, scheduling device, drop control circuit, multicast control circuit and QOS control device
CN100525234C (en) Systems and methods for alleviating client over-subscription in ring networks
JP5077004B2 (en) Communication device, communication system, communication control method, and communication control program
KR100560748B1 (en) method for bandwidth allocation using resilient packet ring fairness mechanism
US5335224A (en) Service guarantees/congestion control in high speed networks
US7096251B2 (en) Calculation of layered routes in a distributed manner
US6310881B1 (en) Method and apparatus for network control
US7289514B2 (en) System and method for scheduling data traffic flows for a communication device
US7307989B2 (en) Window flow control with common time reference
EP1705845B1 (en) Load distributing method
CN100512215C (en) Internal load balancing in a data switch using distributed network processing
US8115617B2 (en) Alarm reordering to handle alarm storms in large networks
CN102075444B (en) Network system and method for guaranteeing multi-type service quality
CN100592707C (en) Token bucket parameters computation for guaranteed services in a data network
CA2462793C (en) Distributed transmission of traffic streams in communication networks

Legal Events

Date Code Title Description
MM4A Annulment or lapse of patent due to non-payment of fees